The paper presents and evaluates a set of local dynamic load balancing strategies inspired to diffusion and characterised by different scopes of locality. The paper shows that poli...
Antonio Corradi, Letizia Leonardi, Franco Zambonel...
The traditional complex access procedure still prevents a lot of scientists to migrate their applications to massively parallel computers and to bene t from their computing power. ...
Abstract. The performance of HPF codes is in uenced by the characteristics of the parallel system and by the e ciency of the compilation system. Performance analysis has to take in...
Maria Calzarossa, Luisa Massari, Alessandro P. Mer...
We propose a tunable scheduling strategy that lies between FIFO and shortest- rst, based on the value of a coe cient Alpha. If Alpha is set to zero then this strategy is just FIFO....
In this paper, we evaluate two different approaches for the compiler-based parallelisation of a C program for MPEG-2 decoding. The first approach experiments with a commercial auto...